Teaching robots to recognize their limits and to correct themselves in order to live and work optimally alongside humans, in homes or factories: this is the ambitious goal of Convince, the European research project coordinated by Italy, with the Italian Institute of Technology (Iit) and which also involves the University of Genoa, the Municipality of Turin and the Turin Museums Foundation. Coordinated by Lorenzo Natale, it is funded with 4 million euros under the Horizon Europe research framework program, promoted by the European Commission.
“A large part of current research focuses on the development of specific capabilities of robots, such as manipulation or locomotion. Instead, we want to shift attention to how to orchestrate these capabilities,” Natale told ANSA. Being able to make robots capable of operating in the real world, made up of continuous unforeseen events and interactions with the external environment, is one of the great unresolved challenges and the Convince project was born to respond to these needs, which in 3 years and mezzo aims to test new technological solutions to improve the autonomy of robots, focusing in particular on three different use cases: a robot vacuum cleaner, a robot for assembling industrial components and a robotic museum guide.
“Those that may seem simple operations for us – said Natale – actually require many different actions, decisions and unforeseen events to deal with”. An example could be to tell a robot to go to the kitchen to get the glass that is on the table: a task that involves moving around, looking for the kitchen, identifying the table and the glass, picking it up and carrying it back and during which they can emerge problems, for example the glass is not on the table or the battery is flat. “What to do? Which choice is the best in this case?” added the researcher. “Some of these unforeseen events – he continued – can already be partially hypothesized by the developers but others cannot be. In this case, the robot must understand that it has a problem ahead of it and seek a solution. Already recognize the anomalous situation and It’s a really important step.” The secret to doing this is to ‘teach’ the robot its limits: what individual parts can and cannot do. Once you become ‘aware’ of the limits it will be possible to correct them.
Source: Ansa
I am a journalist with over 6 years of experience working in the news industry. I currently work as an author for Global Happenings, and my coverage focuses on Technology news. I have written for various publications, including Reuters, The New York Times and The Guardian.
